# Design exercise: Hallucination & Failure Detection

> Unsupported claims, citations, abstention, tool errors, constraint violations, uncertainty, and escalation. Implement designOutline() returning non-empty values for: evidenceCheck, constraintCheck, escalation. Each value must name a concrete mechanism or decision.

Canonical: https://learn.significanthobbies.com/curriculum/drills/practice-hallucination-failure-detection

Unsupported claims, citations, abstention, tool errors, constraint violations, uncertainty, and escalation. Implement designOutline() returning non-empty values for: evidenceCheck, constraintCheck, escalation. Each value must name a concrete mechanism or decision.

## The mechanism

Detect failures against evidence and task constraints. Require citations where possible, validate structured claims, calibrate abstention, and route uncertainty to tools or humans.

## Expected evidence

A design outline with evidenceCheck, constraintCheck, escalation plus an explicit failure mode or trade-off.

## Hints

- Name the failure mode before selecting the mechanism.

## Sources and practice

- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative LLMs](https://arxiv.org/abs/2303.08896)
- [Detecting hallucinations in large language models using semantic entropy (Nature, 2024)](https://www.nature.com/articles/s41586-024-07421-0)
- [Extrinsic Hallucinations in LLMs (Lilian Weng)](https://lilianweng.github.io/posts/2024-07-07-hallucination/)
- [Study Hallucination & Failure Detection](https://learn.significanthobbies.com/curriculum/concepts/hallucination-failure-detection)
- [Try the interactive drill](https://learn.significanthobbies.com/drills/practice-hallucination-failure-detection)
- [All practice briefs](https://learn.significanthobbies.com/curriculum/drills/)